Seaborn Plotting 🤗

Seaborn is a Python data visualization library available on python, based on matplotlib. It provides a high-level interface for drawing attractive and informative statistical graphics.

Functionalities of Seaborn

• Allows comparison between multiple variables
• support multiplot grids
• Available univariate and bivariate visualozation
• Availability of different color palettes to reveal various kind of patterns

Data Visualization using Seaborn

Visualizing statistical relationships

• The process of understanding relationships between variables of a dataset and how this relatioship inturn dependson other variable, this is called a Statistical Analysis

Plotting categorical data

• This approach basically comes into the picture when main variable is further divided into dicrete group. To acheive this, we will use Catplot function available in Seaborn.

Visualizing the distribution of a dataset

• Visualizing dataset basically deal with understanding dataset with cotent to being Univariate or Bivariate.

Importing Libraries

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')

df=pd.read_csv('C:/Users/Admin/Desktop/Innomatics_Internship/Day9/data1.csv')

df.head()

	Unnamed: 0	ID	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
0	train	203097	420000.0	01-06-2012 00:00	present	senior quality engineer	Bangalore	f	19-02-1990 00:00	84.3	...	-1	-1	-1	-1	-1	0.9737	0.8128	0.5269	1.35490	-0.4455
1	train	579905	500000.0	01-09-2013 00:00	present	assistant manager	Indore	m	04-10-1989 00:00	85.4	...	-1	-1	-1	-1	-1	-0.7335	0.3789	1.2396	-0.10760	0.8637
2	train	810601	325000.0	01-06-2014 00:00	present	systems engineer	Chennai	f	03-08-1992 00:00	85.0	...	-1	-1	-1	-1	-1	0.2718	1.7109	0.1637	-0.86820	0.6721
3	train	267447	1100000.0	01-07-2011 00:00	present	senior software engineer	Gurgaon	m	05-12-1989 00:00	85.6	...	-1	-1	-1	-1	-1	0.0464	0.3448	-0.3440	-0.40780	-0.9194
4	train	343523	200000.0	01-03-2014 00:00	01-03-2015 00:00	get	Manesar	m	27-02-1991 00:00	78.0	...	-1	-1	-1	-1	-1	-0.8810	-0.2793	-1.0697	0.09163	-0.1295

5 rows × 39 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3998 entries, 0 to 3997
Data columns (total 39 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   Unnamed: 0             3998 non-null   object 
 1   ID                     3998 non-null   int64  
 2   Salary                 3998 non-null   float64
 3   DOJ                    3998 non-null   object 
 4   DOL                    3998 non-null   object 
 5   Designation            3998 non-null   object 
 6   JobCity                3998 non-null   object 
 7   Gender                 3998 non-null   object 
 8   DOB                    3998 non-null   object 
 9   10percentage           3998 non-null   float64
 10  10board                3998 non-null   object 
 11  12graduation           3998 non-null   int64  
 12  12percentage           3998 non-null   float64
 13  12board                3998 non-null   object 
 14  CollegeID              3998 non-null   int64  
 15  CollegeTier            3998 non-null   int64  
 16  Degree                 3998 non-null   object 
 17  Specialization         3998 non-null   object 
 18  collegeGPA             3998 non-null   float64
 19  CollegeCityID          3998 non-null   int64  
 20  CollegeCityTier        3998 non-null   int64  
 21  CollegeState           3998 non-null   object 
 22  GraduationYear         3998 non-null   int64  
 23  English                3998 non-null   int64  
 24  Logical                3998 non-null   int64  
 25  Quant                  3998 non-null   int64  
 26  Domain                 3998 non-null   float64
 27  ComputerProgramming    3998 non-null   int64  
 28  ElectronicsAndSemicon  3998 non-null   int64  
 29  ComputerScience        3998 non-null   int64  
 30  MechanicalEngg         3998 non-null   int64  
 31  ElectricalEngg         3998 non-null   int64  
 32  TelecomEngg            3998 non-null   int64  
 33  CivilEngg              3998 non-null   int64  
 34  conscientiousness      3998 non-null   float64
 35  agreeableness          3998 non-null   float64
 36  extraversion           3998 non-null   float64
 37  nueroticism            3998 non-null   float64
 38  openess_to_experience  3998 non-null   float64
dtypes: float64(10), int64(17), object(12)
memory usage: 1.0+ MB

df['Unnamed: 0'].unique()

array(['train'], dtype=object)

We are dropping column Unnamed: 0 as it has the same value and column ID as it has unique values

df.drop(columns=['Unnamed: 0','ID'],inplace=True,)

df.head()

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
0	420000.0	01-06-2012 00:00	present	senior quality engineer	Bangalore	f	19-02-1990 00:00	84.3	board ofsecondary education,ap	2007	...	-1	-1	-1	-1	-1	0.9737	0.8128	0.5269	1.35490	-0.4455
1	500000.0	01-09-2013 00:00	present	assistant manager	Indore	m	04-10-1989 00:00	85.4	cbse	2007	...	-1	-1	-1	-1	-1	-0.7335	0.3789	1.2396	-0.10760	0.8637
2	325000.0	01-06-2014 00:00	present	systems engineer	Chennai	f	03-08-1992 00:00	85.0	cbse	2010	...	-1	-1	-1	-1	-1	0.2718	1.7109	0.1637	-0.86820	0.6721
3	1100000.0	01-07-2011 00:00	present	senior software engineer	Gurgaon	m	05-12-1989 00:00	85.6	cbse	2007	...	-1	-1	-1	-1	-1	0.0464	0.3448	-0.3440	-0.40780	-0.9194
4	200000.0	01-03-2014 00:00	01-03-2015 00:00	get	Manesar	m	27-02-1991 00:00	78.0	cbse	2008	...	-1	-1	-1	-1	-1	-0.8810	-0.2793	-1.0697	0.09163	-0.1295

5 rows × 37 columns

df.isnull().sum()

Salary                   0
DOJ                      0
DOL                      0
Designation              0
JobCity                  0
Gender                   0
DOB                      0
10percentage             0
10board                  0
12graduation             0
12percentage             0
12board                  0
CollegeID                0
CollegeTier              0
Degree                   0
Specialization           0
collegeGPA               0
CollegeCityID            0
CollegeCityTier          0
CollegeState             0
GraduationYear           0
English                  0
Logical                  0
Quant                    0
Domain                   0
ComputerProgramming      0
ElectronicsAndSemicon    0
ComputerScience          0
MechanicalEngg           0
ElectricalEngg           0
TelecomEngg              0
CivilEngg                0
conscientiousness        0
agreeableness            0
extraversion             0
nueroticism              0
openess_to_experience    0
dtype: int64

df['DOL'].value_counts()

present             1875
01-04-2015 00:00     573
01-03-2015 00:00     124
01-05-2015 00:00     112
01-01-2015 00:00      99
                    ... 
01-03-2005 00:00       1
01-08-2011 00:00       1
01-06-2009 00:00       1
01-10-2010 00:00       1
01-02-2011 00:00       1
Name: DOL, Length: 67, dtype: int64

We are replacing the values present to current date and time from the column DOL

df["DOL"].replace({"present": pd.datetime.now()}, inplace=True)
df['DOL']=pd.to_datetime(df['DOL'])

df['DOL'].value_counts()

2021-02-06 16:52:50.267224    1875
2015-01-04 00:00:00.000000     573
2015-01-03 00:00:00.000000     124
2015-01-05 00:00:00.000000     112
2015-01-01 00:00:00.000000      99
                              ... 
2015-01-10 00:00:00.000000       1
2010-01-02 00:00:00.000000       1
2010-01-10 00:00:00.000000       1
2011-01-08 00:00:00.000000       1
2005-01-03 00:00:00.000000       1
Name: DOL, Length: 67, dtype: int64

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3998 entries, 0 to 3997
Data columns (total 37 columns):
 #   Column                 Non-Null Count  Dtype         
---  ------                 --------------  -----         
 0   Salary                 3998 non-null   float64       
 1   DOJ                    3998 non-null   object        
 2   DOL                    3998 non-null   datetime64[ns]
 3   Designation            3998 non-null   object        
 4   JobCity                3998 non-null   object        
 5   Gender                 3998 non-null   object        
 6   DOB                    3998 non-null   object        
 7   10percentage           3998 non-null   float64       
 8   10board                3998 non-null   object        
 9   12graduation           3998 non-null   int64         
 10  12percentage           3998 non-null   float64       
 11  12board                3998 non-null   object        
 12  CollegeID              3998 non-null   int64         
 13  CollegeTier            3998 non-null   int64         
 14  Degree                 3998 non-null   object        
 15  Specialization         3998 non-null   object        
 16  collegeGPA             3998 non-null   float64       
 17  CollegeCityID          3998 non-null   int64         
 18  CollegeCityTier        3998 non-null   int64         
 19  CollegeState           3998 non-null   object        
 20  GraduationYear         3998 non-null   int64         
 21  English                3998 non-null   int64         
 22  Logical                3998 non-null   int64         
 23  Quant                  3998 non-null   int64         
 24  Domain                 3998 non-null   float64       
 25  ComputerProgramming    3998 non-null   int64         
 26  ElectronicsAndSemicon  3998 non-null   int64         
 27  ComputerScience        3998 non-null   int64         
 28  MechanicalEngg         3998 non-null   int64         
 29  ElectricalEngg         3998 non-null   int64         
 30  TelecomEngg            3998 non-null   int64         
 31  CivilEngg              3998 non-null   int64         
 32  conscientiousness      3998 non-null   float64       
 33  agreeableness          3998 non-null   float64       
 34  extraversion           3998 non-null   float64       
 35  nueroticism            3998 non-null   float64       
 36  openess_to_experience  3998 non-null   float64       
dtypes: datetime64[ns](1), float64(10), int64(16), object(10)
memory usage: 999.6+ KB

df.isnull().sum()

Salary                   0
DOJ                      0
DOL                      0
Designation              0
JobCity                  0
Gender                   0
DOB                      0
10percentage             0
10board                  0
12graduation             0
12percentage             0
12board                  0
CollegeID                0
CollegeTier              0
Degree                   0
Specialization           0
collegeGPA               0
CollegeCityID            0
CollegeCityTier          0
CollegeState             0
GraduationYear           0
English                  0
Logical                  0
Quant                    0
Domain                   0
ComputerProgramming      0
ElectronicsAndSemicon    0
ComputerScience          0
MechanicalEngg           0
ElectricalEngg           0
TelecomEngg              0
CivilEngg                0
conscientiousness        0
agreeableness            0
extraversion             0
nueroticism              0
openess_to_experience    0
dtype: int64

df.shape

(3998, 37)

df.dtypes

Salary                          float64
DOJ                              object
DOL                      datetime64[ns]
Designation                      object
JobCity                          object
Gender                           object
DOB                              object
10percentage                    float64
10board                          object
12graduation                      int64
12percentage                    float64
12board                          object
CollegeID                         int64
CollegeTier                       int64
Degree                           object
Specialization                   object
collegeGPA                      float64
CollegeCityID                     int64
CollegeCityTier                   int64
CollegeState                     object
GraduationYear                    int64
English                           int64
Logical                           int64
Quant                             int64
Domain                          float64
ComputerProgramming               int64
ElectronicsAndSemicon             int64
ComputerScience                   int64
MechanicalEngg                    int64
ElectricalEngg                    int64
TelecomEngg                       int64
CivilEngg                         int64
conscientiousness               float64
agreeableness                   float64
extraversion                    float64
nueroticism                     float64
openess_to_experience           float64
dtype: object

Dist Plot

• Dist Plot is used to create the histogram
• It helps us to check the distrbution of the columns feature

sns.distplot(df['Salary'])

<AxesSubplot:xlabel='Salary', ylabel='Density'>

Observations:

• Most of the candidates has the salary between 0 to 1 LPA
• We observed that highest salary of the candidate is around 4 LPA

Point Plot

A point plot represents an estimate of central tendency for a numeric variable by the position of scatter plot points and provides some indication of the uncertainty around that estimate using error bars.

Point plots can be more useful than bar plots for focusing comparisons between different levels of one or more categorical variables. They are particularly adept at showing interactions: how the relationship between levels of one categorical variable changes across levels of a second categorical variable. The lines that join each point from the same hue level allow interactions to be judged by differences in slope, which is easier for the eyes than comparing the heights of several groups of points or bars.

sns.pointplot(x="Degree", y= 'GraduationYear', hue="Gender",data=df)

<AxesSubplot:xlabel='Degree', ylabel='GraduationYear'>

Observations:

• Most of the female candidate has persued M.Sc degree in the year 2015 whereas most of the male candidate has persued the same degree in the year 2013.

sns.pointplot(x = df['Degree'].unique(),y = df['Degree'].value_counts(),data=df)

<AxesSubplot:ylabel='Degree'>

Observations:

• Most of the candidates has persued BTech degree and whereas less candidaes has persued M.sc degree.

Categorical Plots

Seaborn also helps us in doing the analysis on Categorical Data points.

• boxplot
• violinplot
• countplot
• barplot

Count Plot

• The Count plot shows the counts of observations in each categorical bin using bars.

• A count plot can be thought of as a histogram across a categorical, instead of quantitative, variable.

sns.countplot('Degree', data=df)

<AxesSubplot:xlabel='Degree', ylabel='count'>

Observations:

• Most of the candidates has persued BTech degree and whereas very less candidaes has persued M.sc degree.

sns.countplot(x='CollegeState',data=df)
plt.xticks(rotation=90)
plt.show()

Observations:

• Most of the candidates has persued their degrees from the colleges of the state Uttar Pradesh, followed by the colleges of the states Karnatka and Tamilnadu.
• There are very few candidates from the colleges of the states Goa, Sikkim and Meghalaya.

sns.countplot(x='CollegeCityTier',hue = 'Gender', data=df)

<AxesSubplot:xlabel='CollegeCityTier', ylabel='count'>

Observations:

• We observed that most of the candidates has persued their degrees from the college located in the 0 tier of the city.
• Also we observed that there are more male candidates in both the Tiers than female candidates.

Bar Plot

• A bar plot represents an estimate of central tendency for a numeric variable with the height of each rectangle and provides some indication of the uncertainty around that estimate using error bars. Bar plots include 0 in the quantitative axis range, and they are a good choice when 0 is a meaningful value for the quantitative variable, and you want to make comparisons against it.

• For datasets where 0 is not a meaningful value, a point plot will allow you to focus on differences between levels of one or more categorical variables.

• It is also important to keep in mind that a bar plot shows only the mean (or other estimator) value, but in many cases it may be more informative to show the distribution of values at each level of the categorical variables. In that case, other approaches such as a box or violin plot may be more appropriate.

sns.barplot(y='Salary',x='Gender', data=df)

<AxesSubplot:xlabel='Gender', ylabel='Salary'>

Observations:

• We observed that the male candidates has the slightly higher salary than the female candidates.

sns.barplot(y='Salary',x='Degree', data=df)

<AxesSubplot:xlabel='Degree', ylabel='Salary'>

Observations:

• We observed that the candidates who has persued M.Tech has the highest salary than any other degrees.
• B.tech and M.Sc candidates has the highest salary of around 3 LPA.

Box Plot

• A box and whisker plot(sometimes called a boxplot) is a graph that presents information from a five-number summary.
• It shows the distributions with respect to categories.
• A box plot (or box-and-whisker plot) shows the distribution of quantitative data in a way that facilitates comparisons between variables or across levels of a categorical variable.
• The box shows the quartiles of the dataset while the whiskers extend to show the rest of the distribution, except for points that are determined to be "outliers" using a method that is a function of the inter-quartile range.

sns.boxplot(x='Degree',y='12percentage',hue='Gender',data=df)

<AxesSubplot:xlabel='Degree', ylabel='12percentage'>

Observations:

• Most of the B.Tech female candidates has scored (70 - 88) percentage of marks whereas most of the B.Tech male candidates has scored (66 - 82) percentage of marks in 12th Examinations.
• Most of the M.Tech female candidates has scored (72 - 88) percentage of marks whereas most of the M.Tech male candidates has scored (66 - 80) percentage of marks in 12th Examinations.
• We observed that very few outlierse(12th percentage is more than 90%) are identified for the male candidate who has persued MCA.

sns.boxplot(x='Gender',y='10percentage',data=df, palette='rainbow')

<AxesSubplot:xlabel='Gender', ylabel='10percentage'>

Observations:

• The 10th percentage of the most of the female candidates lies between (75 - 88)% whereas that of the male candidates lies between (70 - 85)%.
• We have observed that ver few outliers are present for the female candidates who scored less than 58% in 10th examinations.
• Also,male candidates who scored less than 50% in class 10th examinatin is considered to be outliers.

sns.boxplot(df['CollegeState'],df['12graduation'])
plt.xticks(rotation=90)
plt.show()

Joint Plot

Seaborn’s jointplot displays a relationship between 2 variables (bivariate) as well as 1D profiles (univariate) in the margins. This plot is a convenience class that wraps JointGrid.

sns.jointplot(x='12graduation',y='CollegeTier',data=df,kind='hex')

<seaborn.axisgrid.JointGrid at 0xbaa6700>

sns.jointplot(x='12graduation',y='CollegeTier',data=df,kind='reg')

<seaborn.axisgrid.JointGrid at 0xb5c8fa0>

Observations:

• Most of the candidates who has graduated in class 12th in the year 2009 belongs to the college tier 2.

Violin Plot

• Violin plot helps us to see both the distribution of data in terms of kernel density estimation(kde) and the box plot.

• Draw a combination of boxplot and kernel density estimate.

• A violin plot plays a similar role as a box and whisker plot. It shows the distribution of quantitative data across several levels of one (or more) categorical variables such that those distributions can be compared.

• Unlike a box plot, in which all of the plot components correspond to actual datapoints, the violin plot features a kernel density estimation of the underlying distribution.

sns.violinplot(y='Degree',x='Salary', data=df, palette='rainbow')

<AxesSubplot:xlabel='Salary', ylabel='Degree'>

Observations:

• The salary of the most of the candidates lies between (0 - 1) LPA.
• We do not see any outliers for M.Sc degree candidates with respect to their salary.
• We observed that there are lot of outliers present for both the B.Tech and MCA candidates with respect to their salary.

sns.violinplot(x='CollegeCityTier',y='collegeGPA',hue='Gender',data=df)

<AxesSubplot:xlabel='CollegeCityTier', ylabel='collegeGPA'>

Observations:

• The aggregated GPA at graduation for the most of the candidates on both the tier of the city in which the college is located, lies between (55 - 90).
• We observed that there is no outliers for the female candidates of the college city tier 1.

Scatterplot

A scatterplot is perhaps the most common example of visualizing relationships between two variables. Each point shows an observation in the dataset and these observations are represented by dot-like structures. The plot shows the joint distribution of two variables using a cloud of points.

sns.scatterplot(x="collegeGPA", y="Salary", data = df)

<AxesSubplot:xlabel='collegeGPA', ylabel='Salary'>

Observations:

• Most of the candidates whose graduation GPA lies between 50 - 100 has the salaries between 0 to 1 LPA.
• there are few outliers are observed whose salary is around 2.5 to 4 LPA has the graduation GPA of 70 - 80.

sns.scatterplot(x="12percentage", y="Salary", hue = "Gender", data = df)

<AxesSubplot:xlabel='12percentage', ylabel='Salary'>

Observations:

• As per the plot, we observed that Salaries of the candidates(both male and female) doesn't depend on the 12th percentage.
• Most of the cadidates who has scored percentage between 45 - 100 % in the 12th examinations has the salary of 0-1 LPA.
• only few candidate's salary lies between 2.5to 4 LPA, which has been observed.

Boxen Plot

A Boxen Plot is an an enhanced box plot for larger datasets.

This style of plot was originally named a "letter value" plot because it shows a large number of quantiles that are defined as "letter values". It is similar to a box plot in plotting a nonparametric representation of a distribution in which all features correspond to actual observations. By plotting more quantiles, it provides more information about the shape of the distribution, particularly in the tails.

sns.boxenplot(x='Degree',y='Salary',data=df)
plt.xticks(rotation=90)
plt.show()

Observations:

• B.Tech and MCA graduate candidates has the highest salary.
• Most of the outliers are identified in the B.Tech columns

sns.boxenplot(x='CollegeState',y='Salary',data=df)
plt.xticks(rotation=90)
plt.show()

Strip Plot

A strip plot can be drawn on its own, but it is also a good complement to a box or violin plot in cases where you want to show all observations along with some representation of the underlying distribution.

sns.stripplot(x='Degree',y='Salary',data=df)
plt.xticks(rotation=90)
plt.show()

Observations:

• B.Tech graduate candidates has the highest salary.
• Most of the outliers are identified in the B.Tech columns

sns.stripplot(x='12graduation',y='Degree',data=df)

<AxesSubplot:xlabel='12graduation', ylabel='Degree'>

Swarm Plot

This function is similar to :func:stripplot, but the points are adjusted (only along the categorical axis) so that they don't overlap. This gives a better representation of the distribution of values, but it does not scale well to large numbers of observations. This style of plot is sometimes called a "beeswarm".

A swarm plot can be drawn on its own, but it is also a good complement to a box or violin plot in cases where you want to show all observations along with some representation of the underlying distribution.

sns.swarmplot(x=df['Degree'].unique(),y=df['Degree'].value_counts(),data=df)
plt.xticks(rotation=90)
plt.show()

Observations:

• We observed that most of the candidates has persued B.Tech degree whereaes very few has persued M.SC degree.

Pair Plot

A Pairs Plot is also know as scatterplot, in which one variable in the same data row is matched with another variable's value, like this: Pairs plots are just elaborations on this,showing all variables paired with all other variables

sns.pairplot(df)

<seaborn.axisgrid.PairGrid at 0xd8754c0>

Conclusion:

From the dataset, we conclude that

• There are more male candidates as compared to Females.
• Also, highest salary for the male candidates is slightly higher than that of Female candidates.
• Most of the candidates has persued their degrees from the college located in the 0 tier of the city.
• Most of the candidates has persued their degrees from the colleges of the state Uttar Pradesh, followed by the colleges of the states Karnatka and Tamilnadu whereas very few candidates from the colleges of the states Goa, Sikkim and Meghalaya.
• Most of the candidates has persued BTech degree and whereas very less candidaes has persued M.sc degree.
• We also oberved that, most of the candidates has the salary between 0 to 1 LPA and the highest salary of the candidate is around 4 LPA.
• We observed that the candidates who has persued M.Tech has the highest salary than any other degrees.
• Most of the candidates who has graduated in class 12th in the year 2009 belongs to the college tier 2.
• Most of the candidates whose graduation GPA lies between 50 - 100 has the salaries between 0 to 1 LPA and there are few outliers are observed whose salary is around 2.5 to 4 LPA has the graduation GPA of 70 - 80.
• As per the plot, we observed that Salaries of the candidates(both male and female) doesn't depend on the 12th percentage.
• Most of the cadidates who has scored percentage between 45 - 100 % in the 12th examinations has the salary of 0-1 LPA.
• only few candidate's salary lies between 2.5to 4 LPA, which has been observed.